Pothole Detector (YOLOv8)

Fine-tuned yolov8s.pt on the Smartathon pothole dataset (Roboflow Universe) for road pothole detection.

  • mAP50: 0.816
  • mAP50-95: 0.518

Usage

from ultralytics import YOLO
from huggingface_hub import hf_hub_download

weights_path = hf_hub_download(repo_id="samdutse/pothole-yolov8", filename="best.pt")
model = YOLO(weights_path)
results = model.predict("road.jpg")
Downloads last month
52
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Space using Samdutse/pothole-yolov8 1